CN111260624A - Multi-scale infrared small target detection method based on feature matching and scale selection strategy - Google Patents
Multi-scale infrared small target detection method based on feature matching and scale selection strategy Download PDFInfo
- Publication number
- CN111260624A CN111260624A CN202010040446.2A CN202010040446A CN111260624A CN 111260624 A CN111260624 A CN 111260624A CN 202010040446 A CN202010040446 A CN 202010040446A CN 111260624 A CN111260624 A CN 111260624A
- Authority
- CN
- China
- Prior art keywords
- scale
- target
- map
- saliency map
- feature matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Aiming, Guidance, Guns With A Light Source, Armor, Camouflage, And Targets (AREA)
Abstract
The invention relates to a method for detecting a multi-scale infrared small target based on a feature matching and scale selection strategy, which comprises the following steps: the method comprises the following steps that firstly, an IALM method is adopted to decompose an original infrared image, and a foreground part of a target is extracted from the original infrared image; performing Fourier transform on the target foreground image to obtain a magnitude spectrum of the target; performing convolution on the magnitude spectrum by utilizing a Gaussian kernel function to obtain a saliency map of each scale; step four, screening out a salient map highlighted by the target according to the average value of the areas adjacent to the maximum pixel value in each scale map; step five, obtaining an optimal saliency map according to the local maximum information entropy in the selected saliency map; the method for detecting the multi-scale infrared small target based on the characteristic matching and scale selection strategy not only achieves satisfactory effects in the aspects of vision and quantitative evaluation, but also achieves good effects on infrared images with thick cloud layers and high building brightness.
Description
Technical Field
The invention belongs to the technical field of infrared small target detection, and particularly relates to a multi-scale infrared small target detection method based on a feature matching and scale selection strategy.
Background
With the rapid development of infrared guidance systems, infrared small target detection has always been an important and challenging research topic. Small targets are often submerged in a low signal-to-noise ratio, low contrast, non-constant complex background, and in addition, researchers have made much effort due to the fact that infrared small targets are not well characterized, uncertain in brightness, and weak in intensity because of their long imaging distance in the atmosphere, but infrared small target detection remains a challenging task.
Generally, infrared small target detection methods can be divided into two main detection methods, namely single-frame detection and sequence detection. Sequence detection methods such as interframe difference methods, optical flow methods, three-dimensional direction filtering and Bayesian theory perform well when a target has prior knowledge of the shape and position in adjacent frames. However, researchers often employ single frame detection methods, considering that in practical military applications, it is extremely difficult to acquire a priori knowledge.
Typical single frame image detection methods, such as maximum mean and maximum median filters, two-dimensional least mean square filtering, background regression estimation, morphological methods, bilateral filters, can effectively detect objects in a simple background. However, these methods do not achieve satisfactory detection results when small targets are submerged in infrared images with highly heterogeneous backgrounds.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method for detecting a multi-scale infrared small target based on a feature matching and scale selection strategy, which includes the following steps:
the method comprises the following steps that firstly, an IALM method is adopted to decompose an original infrared image, and a foreground part of a target is extracted from the original infrared image;
performing Fourier transform on the target foreground image to obtain a magnitude spectrum of the target;
thirdly, performing convolution on the amplitude spectrum obtained in the second step by using a Gaussian kernel function to obtain a saliency map of each scale;
step four, screening out a salient map highlighted by the target according to the average value of the areas adjacent to the maximum pixel value in each scale map;
and step five, obtaining the optimal saliency map according to the local maximum information entropy in the selected saliency map.
The method comprises the following steps of firstly, decomposing an original infrared image by adopting an IALM method, and extracting a foreground part of a target from the original infrared image.
Secondly, Fourier transform is carried out on the target foreground image to obtain the amplitude spectrum of the target, and the method comprises the following steps:
IA(u,v)=logfft(I(x,y)), (2)
IP(u,v)=angle(fft(I(x,y))) (3)
wherein, IA(u, v) represents the amplitude spectrum of the object, IP(u, v) represents the phase spectrum of the target and (u, v) represents the pixel points.
Thirdly, the amplitude spectrum obtained in the second step is convoluted by utilizing a Gaussian kernel function to obtain a saliency map S of each scalek(x, y), the method is as follows:
Φ(u,v;k)=g(u,v;σ)*IA(u,v), (4)
where Φ (u, v; k) is the scale space, g (u, v; σ) is the Gaussian kernel, whose standard deviation σ is related to the scaling factor k:
Sk(x,y)=ifft{exp(Φ(u,v;k)+i·IP(u,v))} (6)。
fourthly, screening out a salient map highlighted by the target according to the average value of the areas adjacent to the maximum pixel value in each scale map, wherein the method comprises the following steps:
Lk=max(Sk(x,y)) k=1ΛK, (8)
wherein L iskMaximum pixel point, N, in the saliency mapkIs 8 neighborhood points, mkK is set to 16 in the experiment as the average of 8 neighborhood pixel values.
The fifth step of obtaining the optimal saliency map according to the local maximum information entropy in the selected saliency map, the method comprises the following steps:
h (x, y) is information entropy, Λ (x, y) represents a local area adjacent to the pixel point (x, y), the pixel value of the local area is projected to K intervals, pb(x, y) represents the probability that the pixel value is in b bins.
The invention has the beneficial effects that: the multi-scale infrared small target detection method based on the feature matching and scale selection strategy provided by the invention not only achieves satisfactory effects in the aspects of vision and quantitative evaluation, but also achieves better effects on infrared images with thicker cloud layers and higher building brightness. Practical experimental data also shows that IALM and ISSS are key steps of the method, the execution sequence of the two methods cannot be changed to ensure that high detection performance is obtained, and through effective improvement, the detection method has strong robustness and effectiveness on shielding and complex noise in infrared small target detection.
The present invention will be described in further detail below with reference to the accompanying drawings.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting a multi-scale infrared small target based on a feature matching and scale selection strategy.
FIG. 2 is a schematic diagram of extraction of a sparse target foreground image by an IALM.
FIG. 3 is a schematic diagram comparing target and interference pixel values at two scales.
FIG. 4a1,b1Is an original image; a is2,b2A saliency map derived from global entropy; a is3,b3Local entropy derived saliency maps.
FIG. 5 is a schematic diagram of the original image and experimental results.
FIG. 6 is a schematic diagram of ROC curves for different comparative methods.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the intended purpose, the following detailed description of the embodiments, structural features and effects of the present invention will be made with reference to the accompanying drawings and examples.
Example 1
The embodiment provides a method for detecting a multi-scale infrared small target based on a feature matching and scale selection strategy, as shown in fig. 1, which includes the following steps:
the method comprises the following steps that firstly, an IALM method is adopted to decompose an original infrared image, and a foreground part of a target is extracted from the original infrared image;
performing Fourier transform on the target foreground image to obtain a magnitude spectrum of the target;
thirdly, performing convolution on the amplitude spectrum obtained in the second step by using a Gaussian kernel function to obtain a saliency map of each scale;
step four, screening out a salient map highlighted by the target according to the average value of the areas adjacent to the maximum pixel value in each scale map;
and step five, obtaining the optimal saliency map according to the local maximum information entropy in the selected saliency map.
Further, in the first step, the original infrared image is decomposed by adopting an IALM method, and the foreground part of the target is extracted from the original infrared image, and the process is as follows: inputting an observation matrix D, wherein lambda is the weight of a sparse error term; then, updating a low-rank matrix L and a sparse matrix E by using a singular value threshold contraction method; updating a Lagrange multiplier matrix Y, and finally outputting a low-rank matrix L and a sparse matrix E; the sparse matrix E is a target foreground image; the specific process is as follows:
fig. 2 shows the experimental results of three typical infrared small target images after being processed by the IALM method, and the results show that the method can effectively filter out part of uniform background and enhance the target contrast, and in fig. 2, the target area is marked by a circle.
Further, in the second step, fourier transform is performed on the target foreground image to obtain a magnitude spectrum of the target, and the method includes:
IA(u,v)=log|fft(I(x,y))|, (2)
IP(u,v)=angle(fft(I(x,y))) (3)
wherein, I (x, y) represents the target foreground image, namely the sparse matrix E, I obtained in the step oneA(u, v) logarithmic amplitude spectrum, I, of the foreground image of the objectP(u, v) a phase spectrum representing a foreground image of the target; the convolution of the image log-amplitude spectrum with a low-pass gaussian kernel of appropriate scale is equivalent to a saliency detector of the image, so we use gaussian kernel functions of different scales to obtain saliency maps of different scales.
Thirdly, the amplitude spectrum obtained in the second step is convoluted by utilizing a Gaussian kernel function to obtain a saliency map S of each scalek(x, y), the method is as follows:
Φ(u,v;k)=g(u,v;σ)*IA(u,v), (4)
where Φ (u, v; k) is the scale space, g (u, v; σ) is the gaussian kernel, whose standard deviation σ is related to the scale parameter k:
combining the obtained smooth logarithmic amplitude spectrum with the original phase spectrum IP (u, v), calculating inverse Fourier transform to obtain significance mapping Sk(x,y):
Sk(x,y)=ifft{exp(Φ(u,v;k)+i·IP(u,v))} (6)。
Different scales of gaussian kernels are required for detection of salient objects of different sizes, and selection of too small or too large a kernel scale may result in the background region being under-suppressed or the region edges being highlighted. The uniformly distributed large background region requires a small-scale gaussian kernel to smooth the magnitude spectrum for suppression, and a large-scale gaussian kernel is used to detect distant or rich-texture targets. Small objects typically belong to distant and textural objects, so a larger scale gaussian kernel is required. Setting a Gaussian kernel function scale parameter k as a formula (5), wherein when the value of k is small, the standard deviation sigma of the Gaussian kernel function changes slowly, and when the value of k is large, the sigma changes rapidly; this fine-scale segmentation strategy helps to select a suitable and accurate gaussian kernel for small targets.
Further, in the fourth step, a saliency map of the target is screened out according to the average value of the regions adjacent to the maximum pixel value in each scale map, and the method comprises the following steps:
Lk=max(Sk(x,y)) k=1ΛK, (8)
wherein L iskMaximum pixel point in the saliency map, NkIs 8 neighborhood points, mkK is set to 16 in the experiment as the average of 8 neighborhood pixel values.
Further, in the fifth step, an optimal saliency map is obtained according to the local maximum information entropy in the selected saliency map, and the method includes:
h (x, y) is information entropy, Λ (x, y) represents a local area adjacent to the pixel point (x, y), pixel values of the local area are projected onto K intervals, and pb(x, y) represents the probability that the pixel value is in the b interval. Information entropy value of local significant region which is significantly influenced by infrared small targetEntropy is typically used as a quantitative indicator of the information content of the system. The contribution of the infrared small object to the information entropy of the whole image is negligible. For saliency detection of large objects, the minimum image information entropy may well select the optimal saliency map, but it is not suitable for infrared objects of extremely small size.
The similarity of the pixel points is determined by adjacent areas, because background pixel values have continuity, neighborhood pixel values near a strong interference background are similar to each other or tend to be close to a maximum pixel value, and only a few neighborhood pixel values tend to be close to a central pixel value in a small target area. A number of experiments have shown that the average of the pixel values of 8 neighborhoods around the target region is typically smaller than the average in the highlighted background clutter. We set a criterion τ, and when the average is smaller than τ, temporarily store the scale corresponding to the region, and when the average is larger than τ, consider the corresponding map as "insignificant". After traversing all the scale maps, calculating local information entropy in a salient region in the stored scale map, and regarding the scale map corresponding to the maximum local information entropy as an optimal scale kOUT
As shown in fig. 4, a2, b2 of fig. 4 and a3, b3 of fig. 4 respectively show optimal scale saliency maps screened by minimum image entropy and proposed maximum local entropy according to the original SSS method. As shown in fig. 4a1, the saliency map obtained with minimum information entropy focuses on close-range cars, while the proposed selection mechanism focuses on the driver, i.e. a small object in the original image. Similarly, from fig. 4b1, the saliency map obtained by the minimum information entropy method focuses on high-brightness buildings at close distances, while the local information entropy method can effectively detect infrared small targets at far distances.
In order to further objectively verify the detection performance of the method, three evaluation indexes are adopted: signal-to-clutter ratio gain (SCRg), Background Suppression Factor (BSF), and receiver operating characteristic curve (ROC curve)
Wherein, mutIs the average of the target area intensities, μ and σ are the average and standard deviation of the whole image intensity, both SCRg and BSF indicate the accuracy of the infrared small target detection, the larger the values of SCRg and BSF, the better the performance of the correlation method in terms of background suppression and target extraction.
The method for detecting the multi-scale infrared small target based on the feature matching and scale selection strategies is an accurate and stable infrared small target detection method. A large number of experiments show that the method is not only superior to other contrast methods in visual quality, but also superior to other contrast methods in quantitative evaluation standards (such as SCRg, BSF score and ROC curve), and particularly, under the conditions of thick cloud layers and high building brightness, as shown in tables 1, 2, 3 and 6, the method is used for extracting the contrast of the infrared small target from the three images, namely Image a, Image b and Image c, by adopting different methods, so that the result of extracting the infrared small target by the multi-scale infrared small target detection method based on the feature matching and scale selection strategy is superior to other Image processing methods.
TABLE 1 details of the three sequences
TABLE 2 SCRg and BSF values for different comparative methods
TABLE 3 run times for the different comparative methods
The IALM method and the ISSS method are not alternative steps of the method, and their execution order is not interchangeable, as shown in FIG. 5, where a1-c1 are original images. a2-c2 shows the results of an ISSS experiment followed by an IALM experiment; when the execution sequence of the two methods is changed, the false alarm rate of the detection result is high. As a preprocessing step, the ISSS method not only improves the strength of the target, but also sharpens the background edge; therefore, in order to improve the detection performance, the role of the IALM method in the image preprocessing stage is irreplaceable; meanwhile, the ISSS method can further eliminate the residual background at the post-processing stage.
In summary, the multi-scale infrared small target detection method based on the feature matching and scale selection strategy not only achieves satisfactory effects in the aspects of vision and quantitative evaluation, but also achieves good effects on infrared images with thick cloud layers and high building brightness, and actual experimental data also shows that IALM and ISSS are key steps of the method, the execution sequence of the two methods cannot be changed to ensure that high detection performance is obtained, and through effective improvement, the detection method has strong robustness and effectiveness on shielding and complex noise in infrared small target detection.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions may be made without departing from the spirit of the invention, which should be construed as belonging to the scope of the invention.
Claims (5)
1. A multi-scale infrared small target detection method based on feature matching and scale selection strategies is characterized by comprising the following steps:
the method comprises the following steps that firstly, an IALM method is adopted to decompose an original infrared image, and a foreground part of a target is extracted from the original infrared image;
performing Fourier transform on the target foreground image to obtain a magnitude spectrum of the target;
thirdly, performing convolution on the amplitude spectrum obtained in the second step by using a Gaussian kernel function to obtain a saliency map of each scale;
step four, screening out a salient map highlighted by the target according to the average value of the areas adjacent to the maximum pixel value in each scale map;
and step five, obtaining the optimal saliency map according to the local maximum information entropy in the selected saliency map.
2. The method for detecting the multi-scale infrared small target based on the feature matching and scale selection strategy as claimed in claim 1, characterized in that: secondly, Fourier transform is carried out on the target foreground image to obtain the amplitude spectrum of the target, and the method comprises the following steps:
IA(u,v)=log|fft(I(x,y))|, (2)
IP(u,v)=angle(fft(I(x,y))) (3)
wherein, IA(u, v) represents the amplitude spectrum of the object, IP(u, v) represents the phase spectrum of the target and (u, v) represents the pixel points.
3. The method for detecting the multi-scale infrared small target based on the feature matching and scale selection strategy as claimed in claim 1, characterized in that: thirdly, the amplitude spectrum obtained in the second step is convoluted by utilizing a Gaussian kernel function to obtain a saliency map S of each scalek(x, y), the method is as follows:
Φ(u,v;k)=g(u,v;σ)*IA(u,v), (4)
where Φ (u, v; k) is the scale space, g (u, v; σ) is the Gaussian kernel, whose standard deviation σ is related to the scaling factor k:
Sk(x,y)=ifft{exp(Φ(u,v;k)+i·IP(u,v))} (6)
4. the method for detecting the multi-scale infrared small target based on the feature matching and scale selection strategy as claimed in claim 1, characterized in that: step four, screening out a salient map with a target salient according to the average value of the areas adjacent to the maximum pixel value in each scale map, wherein the method comprises the following steps:
Lk=max(Sk(x,y))k=1ΛK, (8)
wherein L iskIs the largest pixel point in the saliency map, NkIs 8 neighborhood points, mkK is set to 16 in the experiment as the average of 8 neighborhood pixel values.
5. The method for detecting the multi-scale infrared small target based on the feature matching and scale selection strategy as claimed in claim 1, characterized in that: the fifth step of obtaining the optimal saliency map according to the local maximum information entropy in the selected saliency map, the method comprises the following steps:
h (x, y) is information entropy, Λ (x, y) represents a local area adjacent to the pixel point (x, y), the pixel value of the local area is projected to K intervals, pb(x, y) represents the probability that the pixel value is in b bins.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010040446.2A CN111260624B (en) | 2020-01-15 | 2020-01-15 | Multi-scale infrared small target detection method based on feature matching and scale selection strategy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010040446.2A CN111260624B (en) | 2020-01-15 | 2020-01-15 | Multi-scale infrared small target detection method based on feature matching and scale selection strategy |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111260624A true CN111260624A (en) | 2020-06-09 |
CN111260624B CN111260624B (en) | 2023-05-26 |
Family
ID=70954036
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010040446.2A Active CN111260624B (en) | 2020-01-15 | 2020-01-15 | Multi-scale infrared small target detection method based on feature matching and scale selection strategy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111260624B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529896A (en) * | 2020-12-24 | 2021-03-19 | 山东师范大学 | Infrared small target detection method and system based on dark channel prior |
CN115908807A (en) * | 2022-11-24 | 2023-04-04 | 中国科学院国家空间科学中心 | Method, system, computer equipment and medium for quickly detecting weak and small targets |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012135043A1 (en) * | 2011-03-25 | 2012-10-04 | Fairfield Industries Incorporated | Detecting structural and stratigraphic information from seismic data |
CN109145914A (en) * | 2018-07-23 | 2019-01-04 | 辽宁工程技术大学 | A kind of conspicuousness object detection method based on supercomplex Fourier transformation and mean shift |
CN109272489A (en) * | 2018-08-21 | 2019-01-25 | 西安电子科技大学 | Inhibit the method for detecting infrared puniness target with multiple dimensioned local entropy based on background |
US20190197344A1 (en) * | 2016-08-03 | 2019-06-27 | Jiangsu University | Saliency-based method for extracting road target from night vision infrared image |
CN110660065A (en) * | 2019-09-29 | 2020-01-07 | 云南电网有限责任公司电力科学研究院 | Infrared fault detection and identification algorithm |
-
2020
- 2020-01-15 CN CN202010040446.2A patent/CN111260624B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012135043A1 (en) * | 2011-03-25 | 2012-10-04 | Fairfield Industries Incorporated | Detecting structural and stratigraphic information from seismic data |
US20190197344A1 (en) * | 2016-08-03 | 2019-06-27 | Jiangsu University | Saliency-based method for extracting road target from night vision infrared image |
CN109145914A (en) * | 2018-07-23 | 2019-01-04 | 辽宁工程技术大学 | A kind of conspicuousness object detection method based on supercomplex Fourier transformation and mean shift |
CN109272489A (en) * | 2018-08-21 | 2019-01-25 | 西安电子科技大学 | Inhibit the method for detecting infrared puniness target with multiple dimensioned local entropy based on background |
CN110660065A (en) * | 2019-09-29 | 2020-01-07 | 云南电网有限责任公司电力科学研究院 | Infrared fault detection and identification algorithm |
Non-Patent Citations (2)
Title |
---|
黄侃等: "基于超复数傅里叶变换的自适应显著性检测", 《计算机应用》 * |
龚俊亮等: "采用尺度空间理论的红外弱小目标检测方法", 《红外与激光工程》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529896A (en) * | 2020-12-24 | 2021-03-19 | 山东师范大学 | Infrared small target detection method and system based on dark channel prior |
CN115908807A (en) * | 2022-11-24 | 2023-04-04 | 中国科学院国家空间科学中心 | Method, system, computer equipment and medium for quickly detecting weak and small targets |
Also Published As
Publication number | Publication date |
---|---|
CN111260624B (en) | 2023-05-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111582089B (en) | Maritime target information fusion method based on satellite infrared and visible light images | |
Nasiri et al. | Infrared small target enhancement based on variance difference | |
CN107808383B (en) | Rapid detection method for SAR image target under strong sea clutter | |
CN109427055B (en) | Remote sensing image sea surface ship detection method based on visual attention mechanism and information entropy | |
CN109447073B (en) | Infrared weak and small target detection method based on tensor robust principal component analysis | |
CN104834915B (en) | A kind of small infrared target detection method under complicated skies background | |
US9031285B2 (en) | Detection of floating objects in maritime video using a mobile camera | |
CN103761731A (en) | Small infrared aerial target detection method based on non-downsampling contourlet transformation | |
CN110110675B (en) | Wavelet domain fractal infrared cirrus cloud detection method fusing edge information | |
CN108229342B (en) | Automatic sea surface ship target detection method | |
CN105184804B (en) | Small targets detection in sea clutter method based on Airborne IR camera Aerial Images | |
CN111260624B (en) | Multi-scale infrared small target detection method based on feature matching and scale selection strategy | |
Wang et al. | Superpixel-based LCM detector for faint ships hidden in strong noise background SAR imagery | |
CN107273803B (en) | Cloud layer image detection method | |
CN114821358A (en) | Optical remote sensing image marine ship target extraction and identification method | |
Zhu et al. | Saliency‐Based Diver Target Detection and Localization Method | |
Liu et al. | The target detection for GPR images based on curve fitting | |
Albrecht et al. | Visual maritime attention using multiple low-level features and Naive Bayes classification | |
CN104200229B (en) | A kind of SAR target discrimination methods of combination sparse features selection | |
CN106960443B (en) | Unsupervised change detection method and device based on full-polarization time sequence SAR image | |
CN109658340A (en) | The SAR image rapid denoising method saved based on RSVD and histogram | |
CN107729903A (en) | SAR image object detection method based on area probability statistics and significance analysis | |
Li et al. | An improved CFAR scheme for man-made target detection in high resolution SAR images | |
CN108805186B (en) | SAR image circular oil depot detection method based on multi-dimensional significant feature clustering | |
CN111027512A (en) | Remote sensing image shore-approaching ship detection and positioning method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |